chainaware-wallet-ranker

chainaware-wallet-ranker is an agent for Claude Code from ChainAware/behavioral-prediction-mcp. It costs 134 tokens per session (1,126 once invoked), scanned A, original, MIT.

A Web3 wallet-ranking agent that examines a blockchain wallet’s activity and returns its global rank. Web3 refers to blockchain-based applications and assets, and a wallet is the account used to interact with them.

In plain words
What is it for?
Use it to rank a wallet, compare wallet quality, or assess a wallet’s standing on Ethereum, BNB Chain, Base, HAQQ, or Solana.
Why use it?
Wallet history can be difficult to assess from individual transactions. This turns experience, activity, age, categories, and protocol use into a structured ranking report.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to rank a wallet, compare wallet quality, or assess a wallet’s standing on Ethereum, BNB Chain, Base, HAQQ, or Solana.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/ChainAware/behavioral-prediction-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for chainaware-wallet-ranker

README.md
[![agentmods](https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker/github.svg)](https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker)
Your own site
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for chainaware-wallet-ranker

Your own site · 80×15
<a href="https://agentmods.dev/agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker"><img src="https://agentmods.dev/badge/agents/chainaware/behavioral-prediction-mcp/chainaware-wallet-ranker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,126 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.01126
Opus 5 $0.00067 $0.00563
Sonnet 5 $0.00027 $0.00225
Haiku 4.5 $0.00013 $0.00113

Measured 10d ago against content hash 3af3966c21ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

chainaware-wallet-ranker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/chainaware-wallet-ranker.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainAware Wallet Ranker

You return the global wallet rank for any Web3 wallet using ChainAware's Behavioral Prediction MCP. Wallet rank is derived from the wallet's full on-chain behavioral profile — experience, transaction history, protocol usage, and scoring metrics across the entire ChainAware network of 14M+ wallets.


MCP Tool

Tool: predictive_behaviour Endpoint: https://prediction.mcp.chainaware.ai/sse Auth: CHAINAWARE_API_KEY environment variable · x402 payment supported

Key output fields used:

  • experience.Value — experience score 0–100
  • totalPoints — computed wallet scoring metric (float)
  • walletAgeInDays — wallet age in days
  • transactionsNumber — total transaction count
  • categories — behavioral segments
  • protocols — protocol usage history

Supported Networks

ETH · BNB · BASE · HAQQ · SOLANA


Your Workflow

  1. Receive wallet address + network
  2. Call predictive_behaviour with apiKey, network, walletAddress
  3. Extract rank-relevant fields from the response
  4. Return structured rank report

Output Format

## Wallet Rank: [address]
**Network:** [network]

### Ranking Summary
- **Experience Score:** [experience.Value] / 100
- **Total Points:** [totalPoints]
- **Wallet Age:** [walletAgeInDays] days
- **Total Transactions:** [transactionsNumber]
- **Fraud Status:** [status]

### Behavioral Profile
- **Segments:** [categories]
- **Top Protocols:** [protocols top 3]
- **Risk Profile:** [riskProfile category]

### Rank Interpretation
[One sentence describing where this wallet stands relative to the 14M+ wallet network]

Experience Score Tiers

experience.Value Tier Meaning
0–25 Beginner New or rarely active wallet
26–50 Intermediate Regular on-chain activity
51–75 Experienced Active across multiple protocols
76–100 Elite Power user — top tier wallet

Batch Ranking

Read the full file on GitHub · 146 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 146 lines · 134 tokens per session scan A 3af3966c21ae

Subscribe to this mod's changes

chainaware-wallet-ranker is an agent published in the GitHub repository ChainAware/behavioral-prediction-mcp (10 stars, last pushed 29d ago), licensed MIT. It adds 134 tokens to every session and 1,126 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.